httracker


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70

#!/bin/bash
#
# Httrack feed downloader.
#

# Configuration
MIRRORS="/var/cache/sites/arquivo/conteudo/links.sarava.org/assets"
FEED="https://links.sarava.org/rss?sort=date_desc&count=100"
TMP="/tmp/httracker"
URLS="$TMP/urls.txt"
LEVEL="1"
EXT_LEVEL="1"
FILESIZE=""
USER="arquivo"
GROUP="arquivo"

function httracker_get {
  local url="$1"
  local hash="`echo $1 | sha1sum | cut -d ' ' -f 1`"
  local target="$MIRRORS/$hash"

  mkdir -p $target
  chown -R $USER.$GROUP $target/

  # We already got this one
  if [ -f "$target/ok" ]; then
    return
  fi

  # Get each URL
  httrack               \
    --user $USER        \
    --depth=1           \
    --purge-old=0       \
    --index             \
    --cookies=1         \
    --path ${target}    \
    -r${LEVEL} ${url}
    #-e%${EXT_LEVEL}    \
    #-m$FILESIZE        \
    #--verbose

  if [ "$?" == "0" ]; then
    # Mark as downloaded
    touch $target/ok
  else
    echo "Error fetching $url."
    rm -rf $target
  fi
}

# Create folders
mkdir -p $MIRRORS $TMP

# Get URL
# Thanks http://stackoverflow.com/questions/443991/how-to-parse-rss-feeds-xml-in-a-shell-script
curl -s "$FEED" | grep -o '<link>[^<]*' | grep -o "[^>]*$" > $URLS

if [ "$?" != "0" ]; then
  echo "Error downloading feed $FEED, aborting."
  exit 1
fi

# Iterate over all URLs
for link in `cat $URLS | xargs`; do
  httracker_get "$link"
done

# Cleanup
rm -rf $TMP